Finetuned from model: Llama3-70B

You can read more about the "LLM curation" via fine tuning with Nostr notes: here and here.

I am using the model here as a ground truth for Nostr related questions: https://wikifreedia.xyz/based-llm-leaderboard/npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c

I have about 1000 questions that I constantly ask the model to track its performance. You can DM me on Nostr to get the answers to some interesting questions. The answers from this model is quite different than majority of models on "topics that matter". This model might be the most "based".

Users (both direct and downstream) should be aware of the risks, biases and limitations of the model. The trainer, developer or uploader of this model does not assume any liability. Use it at your own risk. There is no guarantee that the model will be of any use. It may hallucinate often. The answers of this model will be often unreliable and you should do your own research and compare outputs.

Mostly what makes sense to me. Some books, some videos, some banned videos from youtube.

LLaMa-Factory is used to train using fsdp_qlora technique.

This is version 43003.

You can tip me on Nostr https://primal.net/p/npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c

By using this LLM you are talking to a combination of content from many great producers. Portions of your support may in the future go to these original content producers and authors.

You can chat with newer versions of this model on https://pickabrain.ai .